Publisher's Synopsis
The book aims to demonstrate the effectiveness of federated learning in high-performance information systems and informatics-based solutions for addressing current information support requirements. To address heterogeneity challenges in IoT contexts, it analyses the development of personalized federated learning algorithms capable of mitigating the detrimental consequences of heterogeneity in several dimensions. It includes case studies of IoT-based human activity recognition to demonstrate the efficacy of personalized federated learning for intelligent IoT applications.• Demonstrates how federated learning offers a novel approach to building personalized models from data without invading users' privacy• Describes how federated learning may assist in understanding and learning from user behavior in Internet of Things (IoT) applications while safeguarding user privacy• Presents a detailed analysis of current research on federated learning, providing the reader with a broad understanding of the area• Analyses the need for a personalized federated learning framework in cloud-edge and wireless-edge architecture for intelligent IoT applications• Comprises real-life case illustrations and examples to help consolidate understanding of topics presented in each chapterThis book is recommended for anybody interested in Federated Learning-based Intelligent Algorithms for Smart Communications.
